Downloads · 30 days
66
6% of all-time downloads
julianmb/DeepSeek-V4-Flash-0731-IQ2XXS-STRIX
DeepSeek-V4-Flash-0731-IQ2XXS-STRIX is a text generation model from julianmb. Use it when you need the model to write or continue text. The card lists the license as mit.
Quantized DeepSeek V4 Flash (0731) GGUF for AMD Strix Halo (gfx1151).
Downloads · 30 days
66
6% of all-time downloads
All-time downloads
1.2K
Public
Repo size
86.7 GB
Likes
3
Trending 1
Click a slice to open those files.
.gguf86.7 GB · 100%
From the Hugging Face model README
Quantized DeepSeek V4 Flash (0731) GGUF for AMD Strix Halo (gfx1151).
DeepSeek-V4-Flash-0731-IQ2XXS-w2Q2K-AProjQ8-SExpQ8-OutQ8-imatrix)| Tensor group | Type |
|---|---|
| Attention projections | Q8_0 |
| Shared experts | Q8_0 |
| Output head | Q8_0 |
| Token embedding | F16 |
| Routed gate/up experts | IQ2_XXS |
| Routed down experts | Q2_K |
Run with the julianmb/ds4fa engine on 128 GB Strix Halo:
DS4_ROCM_STREAM_MODEL_CACHE_GB=48 ./ds4 -m DeepSeek-V4-Flash-0731-IQ2XXS-STRIX.gguf -c 512 \
--ssd-streaming --ssd-streaming-cache-experts 32GB \
-p "What is the capital of France?" --think --tokens 60